---

Biography

I am a machine learning researcher with research interests in hypothesis testing and transfer learning. My long-term goal is to develop intelligent systems that can learn knowledge from massive related but different domains automatically. Researching on hypothesis testing and transfer learning is the first step for achieving my long-term goal.

I am a postdoctoral researcher at Australian Artificial Intelligence Institute (AAII), University of Technology Sydney (UTS), Australia, and the recipient of Australian Laureate postdoctoral fellowship. I received my Ph.D. degree in computer science at UTS-AAII in 2020, advised by Dist. Prof. Jie Lu and Prof. Guangquan Zhang.

I was a research intern with the AI Residency Program at RIKEN Center for Advanced Intelligence Project (RIKEN-AIP), working on the robust domain adaptation project with Prof. Masashi Sugiyama, Dr. Gang Niu and Dr. Bo Han. I visited Gatsby Computational Neuroscience Unit at UCL and worked on the hypothesis testing project with Prof. Arthur Gretton, Dr. Dougal J. Sutherland and Wenkai Xu.

I have served as a senior program committee (SPC) member for ECAI and program committee (PC) members for NeurIPS, ICML, ICLR, AISTATS, ACML, AAAI, IJCAI, CIKM, ECAI, FUZZ-IEEE and so on. I also serve as reviewers for many academic journals, such as IEEE-TPAMI, IEEE-TNNLS, IEEE-TFS, PR, AMM and so on. I received the UTS-FEIT HDR Research Excellence Award (2019), Best Student Paper Award of FUZZ-IEEE (2019) and UTS Research Publication Award (2018).

---

Research Interests

My research interests lie in hypothesis testing and transfer learning. My long-term goal is to develop intelligent systems that can learn knowledge from massive related but different domains automatically (e,g., domains drawn from different distributions). Researching on hypothesis testing and transfer learning is the first step for achieving my long-term goal. Specifically, my current research work center around two major topics:

• Two-sample testing: How can we know if training set and test set are from the same distribution?

• Domain adaptation: How can we get accurate predictions when the training set (source domain) is statistically different from the test set (target domain)?

---

Research Experience

• Visiting Researcher (August 2019--November 2019)

Gatsby Computational Neuroscience Unit, UCL, London, UK
Advisor: Prof. Arthur Gretton
Collaborators: Dr. Dougal Sutherland, Wenkai Xu
Project: Learning Deep Kernels for Two Sample Test



• Research Intern (March 2019--July 2019)

Imperfect Information Learning Team, RIKEN-AIP, Tokyo, Japan
Advisor: Prof. Masashi Sugiyama
Collaborators: Dr. Gang Niu and Dr. Bo Han
Project: Wildly Unsupervised Domain Adaptation



• Research Assistant (July 2015--July 2016)

Institute of Statistical Science, School of Statistics,
Dongbei University of Finance and Economics, Dalian, China
Advisor: Prof. Ping Jiang
Collaborators: Prof. Jianzhou Wang, Yiliao Song
Project: Time Series Prediction and Interpolation



• Research Intern (May 2014--September 2014)

State Key Laboratory of Numerical Modeling for Atmospheric Sciences and
Geophysical Fluid Dynamics (LASG),
Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, China
Advisor: Senior Scientist Zhenhai Guo
Collaborators: Dr. Xia Xiao, Dr. Jing Zhao, Dr. Zhongyue Su
Project: Forecasting Long-Term Wind Speed via NWP ensembles

---

Education

• Ph.D. in Computer Science (November 2020)

Faculty of Engineering and Information Technology,
University of Technology Sydney, Sydney, Australia.
Supervised by Dist. Prof. Jie Lu and Prof. Guangquan Zhang



• Master of Science (June 2015)

School of Mathematic and Statistics, Lanzhou University, Lanzhou, China
Supervised by Prof. Jianzhou Wang



• Bachelor of Science (June 2013)

School of Mathematic and Statistics, Lanzhou University, Lanzhou, China

---

Sponsors